Abstract:Generating multiple new concepts remains a challenging problem in the text-to-image task. Current methods often overfit when trained on a small number of samples and struggle with attribute leakage, particularly for class-similar subjects (e.g., two specific dogs). In this paper, we introduce Fuse-and-Refine (FaR), a novel approach that tackles these challenges through two key contributions: Concept Fusion technique and Localized Refinement loss function. Concept Fusion systematically augments the training data by separating reference subjects from backgrounds and recombining them into composite images to increase diversity. This augmentation technique tackles the overfitting problem by mitigating the narrow distribution of the limited training samples. In addition, Localized Refinement loss function is introduced to preserve subject representative attributes by aligning each concept's attention map to its correct region. This approach effectively prevents attribute leakage by ensuring that the diffusion model distinguishes similar subjects without mixing their attention maps during the denoising process. By fine-tuning specific modules at the same time, FaR balances the learning of new concepts with the retention of previously learned knowledge. Empirical results show that FaR not only prevents overfitting and attribute leakage while maintaining photorealism, but also outperforms other state-of-the-art methods.
Abstract:Lifelogging involves continuously capturing personal data through wearable cameras, providing an egocentric view of daily activities. Lifelog retrieval aims to search and retrieve relevant moments from this data, yet existing methods largely overlook activity-level annotations, which capture temporal relationships and enrich semantic understanding. In this work, we introduce LSC-ADL, an ADL-annotated lifelog dataset derived from the LSC dataset, incorporating Activities of Daily Living (ADLs) as a structured semantic layer. Using a semi-automatic approach featuring the HDBSCAN algorithm for intra-class clustering and human-in-the-loop verification, we generate accurate ADL annotations to enhance retrieval explainability. By integrating action recognition into lifelog retrieval, LSC-ADL bridges a critical gap in existing research, offering a more context-aware representation of daily life. We believe this dataset will advance research in lifelog retrieval, activity recognition, and egocentric vision, ultimately improving the accuracy and interpretability of retrieved content. The ADL annotations can be downloaded at https://bit.ly/lsc-adl-annotations.
Abstract:Egocentric video has seen increased interest in recent years, as it is used in a range of areas. However, most existing datasets are limited to a single perspective. In this paper, we present the CASTLE 2024 dataset, a multimodal collection containing ego- and exo-centric (i.e., first- and third-person perspective) video and audio from 15 time-aligned sources, as well as other sensor streams and auxiliary data. The dataset was recorded by volunteer participants over four days in a fixed location and includes the point of view of 10 participants, with an additional 5 fixed cameras providing an exocentric perspective. The entire dataset contains over 600 hours of UHD video recorded at 50 frames per second. In contrast to other datasets, CASTLE 2024 does not contain any partial censoring, such as blurred faces or distorted audio. The dataset is available via https://castle-dataset.github.io/.
Abstract:Noisy labels pose a substantial challenge in machine learning, often resulting in overfitting and poor generalization. Sharpness-Aware Minimization (SAM), as demonstrated in Foret et al. (2021), improves generalization over traditional Stochastic Gradient Descent (SGD) in classification tasks with noisy labels by implicitly slowing noisy learning. While SAM's ability to generalize in noisy environments has been studied in several simplified settings, its full potential in more realistic training settings remains underexplored. In this work, we analyze SAM's behavior at each iteration, identifying specific components of the gradient vector that contribute significantly to its robustness against noisy labels. Based on these insights, we propose SANER (Sharpness-Aware Noise-Explicit Reweighting), an effective variant that enhances SAM's ability to manage noisy fitting rate. Our experiments on CIFAR-10, CIFAR-100, and Mini-WebVision demonstrate that SANER consistently outperforms SAM, achieving up to an 8% increase on CIFAR-100 with 50% label noise.
Abstract:Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/
Abstract:Multi-object tracking (MOT) in computer vision remains a significant challenge, requiring precise localization and continuous tracking of multiple objects in video sequences. This task is crucial for various applications, including action recognition and behavior analysis. Key challenges include occlusion, reidentification, tracking fast-moving objects, and handling camera motion artifacts. Past research has explored tracking-by-detection methods and end-to-end models, with recent attention on tracking-by-attention approaches leveraging transformer architectures. The emergence of data sets that emphasize robust reidentification, such as DanceTrack, has highlighted the need for effective solutions. While memory-based approaches have shown promise, they often suffer from high computational complexity and memory usage. We propose a novel sparse memory approach that selectively stores critical features based on object motion and overlapping awareness, aiming to enhance efficiency while minimizing redundancy. Building upon the MOTRv2 model, a hybrid of tracking-by-attention and tracking-by-detection, we introduce a training-free memory designed to bolster reidentification capabilities and preserve the model's flexibility. Our memory approach achieves significant improvements over MOTRv2 in the DanceTrack test set, demonstrating a gain of 1.1\% in HOTA metrics and 2.1\% in IDF1 score.
Abstract:Polyp segmentation, a critical concern in medical imaging, has prompted numerous proposed methods aimed at enhancing the quality of segmented masks. While current state-of-the-art techniques produce impressive results, the size and computational cost of these models pose challenges for practical industry applications. Recently, the Segment Anything Model (SAM) has been proposed as a robust foundation model, showing promise for adaptation to medical image segmentation. Inspired by this concept, we propose SAM-EG, a framework that guides small segmentation models for polyp segmentation to address the computation cost challenge. Additionally, in this study, we introduce the Edge Guiding module, which integrates edge information into image features to assist the segmentation model in addressing boundary issues from current segmentation model in this task. Through extensive experiments, our small models showcase their efficacy by achieving competitive results with state-of-the-art methods, offering a promising approach to developing compact models with high accuracy for polyp segmentation and in the broader field of medical imaging.
Abstract:Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. Existing methods have relied mostly on visual features to generate the segmentation masks while treating text features as supporting components. This over-reliance on visual features can lead to suboptimal results, especially in complex scenarios where text prompts are ambiguous or context-dependent. To overcome these challenges, we present a novel framework VATEX to improve referring image segmentation by enhancing object and context understanding with Vision-Aware Text Feature. Our method involves using CLIP to derive a CLIP Prior that integrates an object-centric visual heatmap with text description, which can be used as the initial query in DETR-based architecture for the segmentation task. Furthermore, by observing that there are multiple ways to describe an instance in an image, we enforce feature similarity between text variations referring to the same visual input by two components: a novel Contextual Multimodal Decoder that turns text embeddings into vision-aware text features, and a Meaning Consistency Constraint to ensure further the coherent and consistent interpretation of language expressions with the context understanding obtained from the image. Our method achieves a significant performance improvement on three benchmark datasets RefCOCO, RefCOCO+ and G-Ref. Code is available at: https://nero1342.github.io/VATEX\_RIS.
Abstract:In this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context. Our method partitions the input video into temporally consecutive segments with clustering information, enabling the injection of temporal awareness into the clustering process, setting it apart from prior cluster-based summarization methods. The resulting temporal-aware clusters are then utilized to compute the final summary, using simple rules for keyframe selection and frame importance scoring. Experimental results on the SumMe dataset demonstrate the effectiveness of our proposed approach, outperforming existing unsupervised methods and achieving comparable performance to state-of-the-art supervised summarization techniques. Our source code is available for reference at \url{https://github.com/hcmus-thesis-gulu/TAC-SUM}.
Abstract:Video summarization is a crucial research area that aims to efficiently browse and retrieve relevant information from the vast amount of video content available today. With the exponential growth of multimedia data, the ability to extract meaningful representations from videos has become essential. Video summarization techniques automatically generate concise summaries by selecting keyframes, shots, or segments that capture the video's essence. This process improves the efficiency and accuracy of various applications, including video surveillance, education, entertainment, and social media. Despite the importance of video summarization, there is a lack of diverse and representative datasets, hindering comprehensive evaluation and benchmarking of algorithms. Existing evaluation metrics also fail to fully capture the complexities of video summarization, limiting accurate algorithm assessment and hindering the field's progress. To overcome data scarcity challenges and improve evaluation, we propose an unsupervised approach that leverages video data structure and information for generating informative summaries. By moving away from fixed annotations, our framework can produce representative summaries effectively. Moreover, we introduce an innovative evaluation pipeline tailored specifically for video summarization. Human participants are involved in the evaluation, comparing our generated summaries to ground truth summaries and assessing their informativeness. This human-centric approach provides valuable insights into the effectiveness of our proposed techniques. Experimental results demonstrate that our training-free framework outperforms existing unsupervised approaches and achieves competitive results compared to state-of-the-art supervised methods.