Despite the undeniable progress in visual recognition tasks fueled by deep neural networks, there exists recent evidence showing that these models are poorly calibrated, resulting in over-confident predictions. The standard practices of minimizing the cross entropy loss during training promote the predicted softmax probabilities to match the one-hot label assignments. Nevertheless, this yields a pre-softmax activation of the correct class that is significantly larger than the remaining activations, which exacerbates the miscalibration problem. Recent observations from the classification literature suggest that loss functions that embed implicit or explicit maximization of the entropy of predictions yield state-of-the-art calibration performances. Despite these findings, the impact of these losses in the relevant task of calibrating medical image segmentation networks remains unexplored. In this work, we provide a unifying constrained-optimization perspective of current state-of-the-art calibration losses. Specifically, these losses could be viewed as approximations of a linear penalty (or a Lagrangian term) imposing equality constraints on logit distances. This points to an important limitation of such underlying equality constraints, whose ensuing gradients constantly push towards a non-informative solution, which might prevent from reaching the best compromise between the discriminative performance and calibration of the model during gradient-based optimization. Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances. Comprehensive experiments on a variety of public medical image segmentation benchmarks demonstrate that our method sets novel state-of-the-art results on these tasks in terms of network calibration, whereas the discriminative performance is also improved.
相關內容
Despite recent advancements in AI for robotics, grasping remains a partially solved challenge, hindered by the lack of benchmarks and reproducibility constraints. This paper introduces a vision-based grasping framework that can easily be transferred across multiple manipulators. Leveraging Quality-Diversity (QD) algorithms, the framework generates diverse repertoires of open-loop grasping trajectories, enhancing adaptability while maintaining a diversity of grasps. This framework addresses two main issues: the lack of an off-the-shelf vision module for detecting object pose and the generalization of QD trajectories to the whole robot operational space. The proposed solution combines multiple vision modules for 6DoF object detection and tracking while rigidly transforming QD-generated trajectories into the object frame. Experiments on a Franka Research 3 arm and a UR5 arm with a SIH Schunk hand demonstrate comparable performance when the real scene aligns with the simulation used for grasp generation. This work represents a significant stride toward building a reliable vision-based grasping module transferable to new platforms, while being adaptable to diverse scenarios without further training iterations.
Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to interact with questions facilitates the multimodal fusion process, the redundancy of audio-visual parameters tends to reduce the generalization of the inference engine to multiple question-answer pairs in a single video. Indeed, the natural heterogeneous relationship between audiovisuals and text makes the perfect fusion challenging, to prevent high-level audio-visual semantics from weakening the network's adaptability to diverse question types, we propose a framework for performing mutual correlation distillation (MCD) to aid question inference. MCD is divided into three main steps: 1) firstly, the residual structure is utilized to enhance the audio-visual soft associations based on self-attention, then key local audio-visual features relevant to the question context are captured hierarchically by shared aggregators and coupled in the form of clues with specific question vectors. 2) Secondly, knowledge distillation is enforced to align audio-visual-text pairs in a shared latent space to narrow the cross-modal semantic gap. 3) And finally, the audio-visual dependencies are decoupled by discarding the decision-level integrations. We evaluate the proposed method on two publicly available datasets containing multiple question-and-answer pairs, i.e., Music-AVQA and AVQA. Experiments show that our method outperforms other state-of-the-art methods, and one interesting finding behind is that removing deep audio-visual features during inference can effectively mitigate overfitting. The source code is released at //github.com/rikeilong/MCD-forAVQA.
Event cameras that asynchronously output low-latency event streams provide great opportunities for state estimation under challenging situations. Despite event-based visual odometry having been extensively studied in recent years, most of them are based on monocular and few research on stereo event vision. In this paper, we present ESVIO, the first event-based stereo visual-inertial odometry, which leverages the complementary advantages of event streams, standard images and inertial measurements. Our proposed pipeline achieves temporal tracking and instantaneous matching between consecutive stereo event streams, thereby obtaining robust state estimation. In addition, the motion compensation method is designed to emphasize the edge of scenes by warping each event to reference moments with IMU and ESVIO back-end. We validate that both ESIO (purely event-based) and ESVIO (event with image-aided) have superior performance compared with other image-based and event-based baseline methods on public and self-collected datasets. Furthermore, we use our pipeline to perform onboard quadrotor flights under low-light environments. A real-world large-scale experiment is also conducted to demonstrate long-term effectiveness. We highlight that this work is a real-time, accurate system that is aimed at robust state estimation under challenging environments.
In several real-world scenarios like autonomous navigation and mobility, to obtain a better visual understanding of the surroundings, image captioning and object detection play a crucial role. This work introduces a novel multitask learning framework that combines image captioning and object detection into a joint model. We propose TICOD, Transformer-based Image Captioning and Object detection model for jointly training both tasks by combining the losses obtained from image captioning and object detection networks. By leveraging joint training, the model benefits from the complementary information shared between the two tasks, leading to improved performance for image captioning. Our approach utilizes a transformer-based architecture that enables end-to-end network integration for image captioning and object detection and performs both tasks jointly. We evaluate the effectiveness of our approach through comprehensive experiments on the MS-COCO dataset. Our model outperforms the baselines from image captioning literature by achieving a 3.65% improvement in BERTScore.
Pedestrian trajectory prediction plays an important role in autonomous driving systems and robotics. Recent work utilizing prominent deep learning models for pedestrian motion prediction makes limited a priori assumptions about human movements, resulting in a lack of explainability and explicit constraints enforced on predicted trajectories. We present a dynamics-based deep learning framework with a novel asymptotically stable dynamical system integrated into a Transformer-based model. We use an asymptotically stable dynamical system to model human goal-targeted motion by enforcing the human walking trajectory, which converges to a predicted goal position, and to provide the Transformer model with prior knowledge and explainability. Our framework features the Transformer model that works with a goal estimator and dynamical system to learn features from pedestrian motion history. The results show that our framework outperforms prominent models using five benchmark human motion datasets.
Current image-text retrieval methods have demonstrated impressive performance in recent years. However, they still face two problems: the inter-modal matching missing problem and the intra-modal semantic loss problem. These problems can significantly affect the accuracy of image-text retrieval. To address these challenges, we propose a novel method called Cross-modal and Uni-modal Soft-label Alignment (CUSA). Our method leverages the power of uni-modal pre-trained models to provide soft-label supervision signals for the image-text retrieval model. Additionally, we introduce two alignment techniques, Cross-modal Soft-label Alignment (CSA) and Uni-modal Soft-label Alignment (USA), to overcome false negatives and enhance similarity recognition between uni-modal samples. Our method is designed to be plug-and-play, meaning it can be easily applied to existing image-text retrieval models without changing their original architectures. Extensive experiments on various image-text retrieval models and datasets, we demonstrate that our method can consistently improve the performance of image-text retrieval and achieve new state-of-the-art results. Furthermore, our method can also boost the uni-modal retrieval performance of image-text retrieval models, enabling it to achieve universal retrieval. The code and supplementary files can be found at //github.com/lerogo/aaai24_itr_cusa.
Controlling robotic manipulators via visual feedback requires a known coordinate frame transformation between the robot and the camera. Uncertainties in mechanical systems as well as camera calibration create errors in this coordinate frame transformation. These errors result in poor localization of robotic manipulators and create a significant challenge for applications that rely on precise interactions between manipulators and the environment. In this work, we estimate the camera-to-base transform and joint angle measurement errors for surgical robotic tools using an image based insertion-shaft detection algorithm and probabilistic models. We apply our proposed approach in both a structured environment as well as an unstructured environment and measure to demonstrate the efficacy of our methods.
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the concept of prompt learning -- a recent trend in NLP -- to the vision domain for adapting pre-trained vision-language models. Specifically, CoOp turns context words in a prompt into a set of learnable vectors and, with only a few labeled images for learning, can achieve huge improvements over intensively-tuned manual prompts. In our study we identify a critical problem of CoOp: the learned context is not generalizable to wider unseen classes within the same dataset, suggesting that CoOp overfits base classes observed during training. To address the problem, we propose Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector). Compared to CoOp's static prompts, our dynamic prompts adapt to each instance and are thus less sensitive to class shift. Extensive experiments show that CoCoOp generalizes much better than CoOp to unseen classes, even showing promising transferability beyond a single dataset; and yields stronger domain generalization performance as well. Code is available at //github.com/KaiyangZhou/CoOp.
Search in social networks such as Facebook poses different challenges than in classical web search: besides the query text, it is important to take into account the searcher's context to provide relevant results. Their social graph is an integral part of this context and is a unique aspect of Facebook search. While embedding-based retrieval (EBR) has been applied in eb search engines for years, Facebook search was still mainly based on a Boolean matching model. In this paper, we discuss the techniques for applying EBR to a Facebook Search system. We introduce the unified embedding framework developed to model semantic embeddings for personalized search, and the system to serve embedding-based retrieval in a typical search system based on an inverted index. We discuss various tricks and experiences on end-to-end optimization of the whole system, including ANN parameter tuning and full-stack optimization. Finally, we present our progress on two selected advanced topics about modeling. We evaluated EBR on verticals for Facebook Search with significant metrics gains observed in online A/B experiments. We believe this paper will provide useful insights and experiences to help people on developing embedding-based retrieval systems in search engines.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191