State-of-the-art systems neuroscience experiments yield large-scale multimodal data, and these data sets require new tools for analysis. Inspired by the success of large pretrained models in vision and language domains, we reframe the analysis of large-scale, cellular-resolution neuronal spiking data into an autoregressive spatiotemporal generation problem. Neuroformer is a multimodal, multitask generative pretrained transformer (GPT) model that is specifically designed to handle the intricacies of data in systems neuroscience. It scales linearly with feature size, can process an arbitrary number of modalities, and is adaptable to downstream tasks, such as predicting behavior. We first trained Neuroformer on simulated datasets, and found that it both accurately predicted simulated neuronal circuit activity, and also intrinsically inferred the underlying neural circuit connectivity, including direction. When pretrained to decode neural responses, the model predicted the behavior of a mouse with only few-shot fine-tuning, suggesting that the model begins learning how to do so directly from the neural representations themselves, without any explicit supervision. We used an ablation study to show that joint training on neuronal responses and behavior boosted performance, highlighting the model's ability to associate behavioral and neural representations in an unsupervised manner. These findings show that Neuroformer can analyze neural datasets and their emergent properties, informing the development of models and hypotheses associated with the brain.
相關內容
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or specification-based fine-tuning, from which we observe the following issues: 1) Generation alternation towards erosion: Parameter drift during target elimination causes alternations and potential deformations across all generations, even eroding other concepts at varying degrees, which is more evident with multi-concept erased; 2) Transfer inability & deployment inefficiency: Previous model-specific erasure impedes the flexible combination of concepts and the training-free transfer towards other models, resulting in linear cost growth as the deployment scenarios increase. To achieve non-invasive, precise, customizable, and transferable elimination, we ground our erasing framework on one-dimensional adapters to erase multiple concepts from most DMs at once across versatile erasing applications. The concept-SemiPermeable structure is injected as a Membrane (SPM) into any DM to learn targeted erasing, and meantime the alteration and erosion phenomenon is effectively mitigated via a novel Latent Anchoring fine-tuning strategy. Once obtained, SPMs can be flexibly combined and plug-and-play for other DMs without specific re-tuning, enabling timely and efficient adaptation to diverse scenarios. During generation, our Facilitated Transport mechanism dynamically regulates the permeability of each SPM to respond to different input prompts, further minimizing the impact on other concepts. Quantitative and qualitative results across ~40 concepts, 7 DMs and 4 erasing applications have demonstrated the superior erasing of SPM. Our code and pre-tuned SPMs will be available on the project page //lyumengyao.github.io/projects/spm.
Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i.e., yielding edge-blurring effect or unrecognizable for object detectors. To alleviate these issues, we propose a semantic structure-preserving approach for IVIF, namely SSPFusion. At first, we design a Structural Feature Extractor (SFE) to extract the structural features of infrared and visible images. Then, we introduce a multi-scale Structure-Preserving Fusion (SPF) module to fuse the structural features of infrared and visible images, while maintaining the consistency of semantic structures between the fusion and source images. Owing to these two effective modules, our method is able to generate high-quality fusion images from pairs of infrared and visible images, which can boost the performance of downstream computer-vision tasks. Experimental results on three benchmarks demonstrate that our method outperforms eight state-of-the-art image fusion methods in terms of both qualitative and quantitative evaluations. The code for our method, along with additional comparison results, will be made available at: //github.com/QiaoYang-CV/SSPFUSION.
Unsupervised depth completion methods are trained by minimizing sparse depth and image reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data augmentation schemes that affect image reconstruction quality, and thus the training signal. Hence, typical augmentations on images viewed as essential to training pipelines in other vision tasks have seen limited use beyond small image intensity changes and flipping. The sparse depth modality have seen even less as intensity transformations alter the scale of the 3D scene, and geometric transformations may decimate the sparse points during resampling. We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth completion. This is achieved by reversing, or ``undo"-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame. This enables computing the reconstruction losses using the original images and sparse depth maps, eliminating the pitfalls of naive loss computation on the augmented inputs. This simple yet effective strategy allows us to scale up augmentations to boost performance. We demonstrate our method on indoor (VOID) and outdoor (KITTI) datasets where we improve upon three existing methods by an average of 11.75% across both datasets.
MARS: Multi-Scale Adaptive Robotics Vision for Underwater Object Detection and Domain Generalization
Underwater robotic vision encounters significant challenges, necessitating advanced solutions to enhance performance and adaptability. This paper presents MARS (Multi-Scale Adaptive Robotics Vision), a novel approach to underwater object detection tailored for diverse underwater scenarios. MARS integrates Residual Attention YOLOv3 with Domain-Adaptive Multi-Scale Attention (DAMSA) to enhance detection accuracy and adapt to different domains. During training, DAMSA introduces domain class-based attention, enabling the model to emphasize domain-specific features. Our comprehensive evaluation across various underwater datasets demonstrates MARS's performance. On the original dataset, MARS achieves a mean Average Precision (mAP) of 58.57\%, showcasing its proficiency in detecting critical underwater objects like echinus, starfish, holothurian, scallop, and waterweeds. This capability holds promise for applications in marine robotics, marine biology research, and environmental monitoring. Furthermore, MARS excels at mitigating domain shifts. On the augmented dataset, which incorporates all enhancements (+Domain +Residual+Channel Attention+Multi-Scale Attention), MARS achieves an mAP of 36.16\%. This result underscores its robustness and adaptability in recognizing objects and performing well across a range of underwater conditions. The source code for MARS is publicly available on GitHub at //github.com/LyesSaadSaoud/MARS-Object-Detection/
This paper introduces Hardcaml, an embedded hardware design domain specific language (DSL) implemented in the OCaml programming language. Unlike high level synthesis (HLS), Hardcaml allows for low level control of the underlying hardware for maximum productivity, while abstracting away many of the tedious aspects of traditional hardware definition languages (HDLs) such as Verilog or VHDL. The richness of OCaml's type system combined with Hardcaml's fast circuit elaboration checks reduces the chance of user-introduced bugs and erroneous connections with features like custom type defining, type-safe parameterized modules and elaboration-time bit-width inference and validation. Hardcaml tooling emphasizes fast feedback through simulation, testing, and verification. It includes both a native OCaml cycle-accurate and an event-driven simulator. Unit tests can live in the source code and include digital ASCII waveforms representing the simulator's output. Hardcaml also provides tools for SAT proving and formal verification. Hardcaml is industrially proven, and has been used at Jane Street internally for many large FPGA designs. As a case study we highlight several aspects of our recent Hardcaml submission to the 2022 ZPrize cryptography competition which won 1st place in the FPGA track.
In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIESCORE, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIESCORE leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIESCORE on seven prominent tasks in conditional image tasks and found: (1) VIESCORE (GPT4-v) achieves a high Spearman correlation of 0.3 with human evaluations, while the human-to-human correlation is 0.45. (2) VIESCORE (with open-source MLLM) is significantly weaker than GPT-4v in evaluating synthetic images. (3) VIESCORE achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIESCORE shows its great potential to replace human judges in evaluating image synthesis tasks.
The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by recent advances in foundation models for vision and language, we propose a multi-embodiment, multi-task generalist agent for robotic manipulation. This agent, named RoboCat, is a visual goal-conditioned decision transformer capable of consuming action-labelled visual experience. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task. We also show how a trained model itself can be used to generate data for subsequent training iterations, thus providing a basic building block for an autonomous improvement loop. We investigate the agent's capabilities, with large-scale evaluations both in simulation and on three different real robot embodiments. We find that as we grow and diversify its training data, RoboCat not only shows signs of cross-task transfer, but also becomes more efficient at adapting to new tasks.
When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly incoming graphs. In response, Continual Graph Learning emerges as a novel paradigm enabling graph representation learning from static to streaming graphs. Our prior work, CaT is a replay-based framework with a balanced continual learning procedure, which designs a small yet effective memory bank for replaying data by condensing incoming graphs. Although the CaT alleviates the catastrophic forgetting problem, there exist three issues: (1) The graph condensation algorithm derived in CaT only focuses on labelled nodes while neglecting abundant information carried by unlabelled nodes; (2) The continual training scheme of the CaT overemphasises on the previously learned knowledge, limiting the model capacity to learn from newly added memories; (3) Both the condensation process and replaying process of the CaT are time-consuming. In this paper, we propose a psudo-label guided memory bank (PUMA) CGL framework, extending from the CaT to enhance its efficiency and effectiveness by overcoming the above-mentioned weaknesses and limits. To fully exploit the information in a graph, PUMA expands the coverage of nodes during graph condensation with both labelled and unlabelled nodes. Furthermore, a training-from-scratch strategy is proposed to upgrade the previous continual learning scheme for a balanced training between the historical and the new graphs. Besides, PUMA uses a one-time prorogation and wide graph encoders to accelerate the graph condensation and the graph encoding process in the training stage to improve the efficiency of the whole framework. Extensive experiments on four datasets demonstrate the state-of-the-art performance and efficiency over existing methods.
This work proposes a neural network to extensively exploit spatial information for multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In the short-time Fourier transform (STFT) domain, the proposed network performs end-to-end speech enhancement. It is mainly composed of interleaved narrow-band and cross-band blocks to respectively exploit narrow-band and cross-band spatial information. The narrow-band blocks process frequencies independently, and use self-attention mechanism and temporal convolutional layers to respectively perform spatial-feature-based speaker clustering and temporal smoothing/filtering. The cross-band blocks process frames independently, and use full-band linear layer and frequency convolutional layers to respectively learn the correlation between all frequencies and adjacent frequencies. Experiments are conducted on various simulated and real datasets, and the results show that 1) the proposed network achieves the state-of-the-art performance on almost all tasks; 2) the proposed network suffers little from the spectral generalization problem; and 3) the proposed network is indeed performing speaker clustering (demonstrated by attention maps).
Existing few-shot learning (FSL) methods assume that there exist sufficient training samples from source classes for knowledge transfer to target classes with few training samples. However, this assumption is often invalid, especially when it comes to fine-grained recognition. In this work, we define a new FSL setting termed few-shot fewshot learning (FSFSL), under which both the source and target classes have limited training samples. To overcome the source class data scarcity problem, a natural option is to crawl images from the web with class names as search keywords. However, the crawled images are inevitably corrupted by large amount of noise (irrelevant images) and thus may harm the performance. To address this problem, we propose a graph convolutional network (GCN)-based label denoising (LDN) method to remove the irrelevant images. Further, with the cleaned web images as well as the original clean training images, we propose a GCN-based FSL method. For both the LDN and FSL tasks, a novel adaptive aggregation GCN (AdarGCN) model is proposed, which differs from existing GCN models in that adaptive aggregation is performed based on a multi-head multi-level aggregation module. With AdarGCN, how much and how far information carried by each graph node is propagated in the graph structure can be determined automatically, therefore alleviating the effects of both noisy and outlying training samples. Extensive experiments show the superior performance of our AdarGCN under both the new FSFSL and the conventional FSL settings.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191