This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving. Due to the lack of semantic modeling capacity in audio and video, existing works have mainly focused on text-based multi-object tracking, which often comes at the cost of tracking quality, interaction efficiency, and even the safety of assistance systems, limiting the application of such methods in autonomous driving. In this paper, we delve into the problem of AR-MOT from the perspective of audio-video fusion and audio-video tracking. We put forward EchoTrack, an end-to-end AR-MOT framework with dual-stream vision transformers. The dual streams are intertwined with our Bidirectional Frequency-domain Cross-attention Fusion Module (Bi-FCFM), which bidirectionally fuses audio and video features from both frequency- and spatiotemporal domains. Moreover, we propose the Audio-visual Contrastive Tracking Learning (ACTL) regime to extract homogeneous semantic features between expressions and visual objects by learning homogeneous features between different audio and video objects effectively. Aside from the architectural design, we establish the first set of large-scale AR-MOT benchmarks, including Echo-KITTI, Echo-KITTI+, and Echo-BDD. Extensive experiments on the established benchmarks demonstrate the effectiveness of the proposed EchoTrack and its components. The source code and datasets are available at //github.com/lab206/EchoTrack.
相關內容
Classification tasks are typically handled using Machine Learning (ML) models, which lack a balance between accuracy and interpretability. This paper introduces a new approach to using Large Language Models (LLMs) for classification tasks in an explainable way. Unlike ML models that rely heavily on data cleaning and feature engineering, this method streamlines the process using LLMs. This paper proposes a new concept called "Language Model Learning (LML)" powered by a new method called "Data-Augmented Prediction (DAP)". The classification is performed by LLMs using a method similar to humans manually exploring and understanding the data and deciding classifications using data as a reference. In the LML process, a dataset is summarized and evaluated to determine the features that lead to the classification of each label the most. In the process of DAP, the system uses the data summary and a row of the testing dataset to automatically generate a query, which is used to retrieve relevant rows from the dataset. A classification is generated by the LLM using data summary and relevant rows, ensuring satisfactory accuracy even with complex data using context-aware decision-making. LML and DAP unlock the possibilities of new applications. The proposed method uses the words "Act as an Explainable Machine Learning Model" in the prompt to enhance the interpretability of the predictions by allowing users to review the logic behind each prediction. In some test cases, the system scored an accuracy above 90%, proving the effectiveness of the system and its potential to outperform conventional ML models in various scenarios. The code is available at //github.com/Pro-GenAI/LML-DAP
Information Retrieval (IR) methods aim to identify relevant documents in response to a given query, which have gained remarkable attention due to their successful application in various natural language tasks. However, existing approaches typically consider only the textual information within the documents, which overlooks the fact that documents can contain multiple modalities, including texts, images, and tables. Further, they often segment each long document into multiple discrete passages for embedding, preventing them from capturing the overall document context and interactions between paragraphs. We argue that these two limitations lead to suboptimal document representations for retrieval. In this work, to address them, we aim to produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities. Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation. Moreover, to mitigate the information loss from segmenting documents into passages, instead of representing and retrieving passages individually, we further merge the representations of segmented passages into one single document representation, while we additionally introduce a reranking strategy to decouple and identify the relevant passage within the document if necessary. Then, through extensive experiments on diverse information retrieval scenarios considering both the textual and multimodal queries, we show that our approach substantially outperforms relevant baselines, thanks to the consideration of the multimodal information interleaved within the documents in a unified way.
We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibration, improving robustness and mitigating semantic inconsistencies introduced by random chunking. Leveraging this insight, we propose an efficient unsupervised learning technique to train the retrieval model, alongside an effective data sampling and scaling strategy. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results while using only 4% of the training data compared to other advanced open-source retrieval models under distribution shift settings. Our method demonstrates strong calibration through span uncertainty, leading to improved generalization and robustness in long-context RAG tasks. Additionally, UncertaintyRAG provides a lightweight retrieval model that can be integrated into any large language model with varying context window lengths, without the need for fine-tuning, showcasing the flexibility of our approach.
HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformer
Numerous studies have demonstrated the strong performance of Vision Transformer (ViT)-based methods across various computer vision tasks. However, ViT models often struggle to effectively capture high-frequency components in images, which are crucial for detecting small targets and preserving edge details, especially in complex scenarios. This limitation is particularly challenging in colon polyp segmentation, where polyps exhibit significant variability in structure, texture, and shape. High-frequency information, such as boundary details, is essential for achieving precise semantic segmentation in this context. To address these challenges, we propose HiFiSeg, a novel network for colon polyp segmentation that enhances high-frequency information processing through a global-local vision transformer framework. HiFiSeg leverages the pyramid vision transformer (PVT) as its encoder and introduces two key modules: the global-local interaction module (GLIM) and the selective aggregation module (SAM). GLIM employs a parallel structure to fuse global and local information at multiple scales, effectively capturing fine-grained features. SAM selectively integrates boundary details from low-level features with semantic information from high-level features, significantly improving the model's ability to accurately detect and segment polyps. Extensive experiments on five widely recognized benchmark datasets demonstrate the effectiveness of HiFiSeg for polyp segmentation. Notably, the mDice scores on the challenging CVC-ColonDB and ETIS datasets reached 0.826 and 0.822, respectively, underscoring the superior performance of HiFiSeg in handling the specific complexities of this task.
We propose the Medial Skeletal Diagram, a novel skeletal representation that tackles the prevailing issues around skeleton sparsity and reconstruction accuracy in existing skeletal representations. Our approach augments the continuous elements in the medial axis representation to effectively shift the complexity away from the discrete elements. To that end, we introduce generalized enveloping primitives, an enhancement over the standard primitives in the medial axis, which ensure efficient coverage of intricate local features of the input shape and substantially reduce the number of discrete elements required. Moreover, we present a computational framework for constructing a medial skeletal diagram from an arbitrary closed manifold mesh. Our optimization pipeline ensures that the resulting medial skeletal diagram comprehensively covers the input shape with the fewest primitives. Additionally, each optimized primitive undergoes a post-refinement process to guarantee an accurate match with the source mesh in both geometry and tessellation. We validate our approach on a comprehensive benchmark of 100 shapes, demonstrating the sparsity of the discrete elements and superior reconstruction accuracy across a variety of cases. Finally, we exemplify the versatility of our representation in downstream applications such as shape generation, mesh decomposition, shape optimization, mesh alignment, mesh compression, and user-interactive design.
Handling long input contexts remains a significant challenge for Large Language Models (LLMs), particularly in resource-constrained environments such as mobile devices. Our work aims to address this limitation by introducing InfiniPot, a novel KV cache control framework designed to enable pre-trained LLMs to manage extensive sequences within fixed memory constraints efficiently, without requiring additional training. InfiniPot leverages Continual Context Distillation (CCD), an iterative process that compresses and retains essential information through novel importance metrics, effectively maintaining critical data even without access to future context. Our comprehensive evaluations indicate that InfiniPot significantly outperforms models trained for long contexts in various NLP tasks, establishing its efficacy and versatility. This work represents a substantial advancement toward making LLMs applicable to a broader range of real-world scenarios.
We propose a novel method to enhance the accuracy of the Iterative Closest Point (ICP) algorithm by integrating altitude constraints from a barometric pressure sensor. While ICP is widely used in mobile robotics for Simultaneous Localization and Mapping ( SLAM ), it is susceptible to drift, especially in underconstrained environments such as vertical shafts. To address this issue, we propose to augment ICP with altimeter measurements, reliably constraining drifts along the gravity vector. To demonstrate the potential of altimetry in SLAM , we offer an analysis of calibration procedures and noise sensitivity of various pressure sensors, improving measurements to centimeter-level accuracy. Leveraging this accuracy, we propose a novel ICP formulation that integrates altitude measurements along the gravity vector, thus simplifying the optimization problem to 3-Degree Of Freedom (DOF). Experimental results from real-world deployments demonstrate that our method reduces vertical drift by 84% and improves overall localization accuracy compared to state-of-the-art methods in non-planar environments.
We present CD-NGP, which is a fast and scalable representation for 3D reconstruction and novel view synthesis in dynamic scenes. Inspired by continual learning, our method first segments input videos into multiple chunks, followed by training the model chunk by chunk, and finally, fuses features of the first branch and subsequent branches. Experiments on the prevailing DyNeRF dataset demonstrate that our proposed novel representation reaches a great balance between memory consumption, model size, training speed, and rendering quality. Specifically, our method consumes $85\%$ less training memory ($<14$GB) than offline methods and requires significantly lower streaming bandwidth ($<0.4$MB/frame) than other online alternatives.
Despite many recent works on Mixture of Experts (MoEs) for resource-efficient Transformer language models, existing methods mostly focus on MoEs for feedforward layers. Previous attempts at extending MoE to the self-attention layer fail to match the performance of the parameter-matched baseline. Our novel SwitchHead is an effective MoE method for the attention layer that successfully reduces both the compute and memory requirements, achieving wall-clock speedup, while matching the language modeling performance of the baseline Transformer. Our novel MoE mechanism allows SwitchHead to compute up to 8 times fewer attention matrices than the standard Transformer. SwitchHead can also be combined with MoE feedforward layers, resulting in fully-MoE "SwitchAll" Transformers. For our 262M parameter model trained on C4, SwitchHead matches the perplexity of standard models with only 44% compute and 27% memory usage. Zero-shot experiments on downstream tasks confirm the performance of SwitchHead, e.g., achieving more than 3.5% absolute improvements on BliMP compared to the baseline with an equal compute resource.
Aspect Sentiment Triplet Extraction (ASTE) aims to co-extract the sentiment triplets in a given corpus. Existing approaches within the pretraining-finetuning paradigm tend to either meticulously craft complex tagging schemes and classification heads, or incorporate external semantic augmentation to enhance performance. In this study, we, for the first time, re-evaluate the redundancy in tagging schemes and the internal enhancement in pretrained representations. We propose a method to improve and utilize pretrained representations by integrating a minimalist tagging scheme and a novel token-level contrastive learning strategy. The proposed approach demonstrates comparable or superior performance compared to state-of-the-art techniques while featuring a more compact design and reduced computational overhead. Additionally, we are the first to formally evaluate GPT-4's performance in few-shot learning and Chain-of-Thought scenarios for this task. The results demonstrate that the pretraining-finetuning paradigm remains highly effective even in the era of large language models.
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