Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent works explore vision-language pre-training to handle this task, but suffer from unrealistic assumptions in practical scenarios, i.e., low-quality textual category names. For example, this paradigm assumes that new textual categories will be accurately and completely provided, and exist in lexicons during pre-training. However, exceptions often happen when meet with ambiguity for brief or incomplete names, new words that are not present in the pre-trained lexicons, and difficult-to-describe categories for users. To address these issues, this work proposes a novel decomposition-aggregation framework, inspired by human cognition in understanding new concepts. Specifically, in the decomposition stage, we decouple class names into diverse attribute descriptions to enrich semantic contexts. Two attribute construction strategies are designed: using large language models for common categories, and involving manually labelling for human-invented categories. In the aggregation stage, we group diverse attributes into an integrated global description, to form a discriminative classifier that distinguishes the target object from others. One hierarchical aggregation is further designed to achieve multi-level alignment and deep fusion between vision and text. The final result is obtained by computing the embedding similarity between aggregated attributes and images. To evaluate the effectiveness, we annotate three datasets with attribute descriptions, and conduct extensive experiments and ablation studies. The results show the superior performance of attribute decomposition-aggregation.

Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation

The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convolution and inadequate fusion of audio-visual features. To overcome these issues, we propose a novel \textbf{Au}dio-aware query-enhanced \textbf{TR}ansformer (AuTR) to tackle the task. Unlike existing methods, our approach introduces a multimodal transformer architecture that enables deep fusion and aggregation of audio-visual features. Furthermore, we devise an audio-aware query-enhanced transformer decoder that explicitly helps the model focus on the segmentation of the pinpointed sounding objects based on audio signals, while disregarding silent yet salient objects. Experimental results show that our method outperforms previous methods and demonstrates better generalization ability in multi-sound and open-set scenarios.

Multi-Modal Prototypes for Open-Set Semantic Segmentation

In semantic segmentation, adapting a visual system to novel object categories at inference time has always been both valuable and challenging. To enable such generalization, existing methods rely on either providing several support examples as visual cues or class names as textual cues. Through the development is relatively optimistic, these two lines have been studied in isolation, neglecting the complementary intrinsic of low-level visual and high-level language information. In this paper, we define a unified setting termed as open-set semantic segmentation (O3S), which aims to learn seen and unseen semantics from both visual examples and textual names. Our pipeline extracts multi-modal prototypes for segmentation task, by first single modal self-enhancement and aggregation, then multi-modal complementary fusion. To be specific, we aggregate visual features into several tokens as visual prototypes, and enhance the class name with detailed descriptions for textual prototype generation. The two modalities are then fused to generate multi-modal prototypes for final segmentation. On both \pascal and \coco datasets, we conduct extensive experiments to evaluate the framework effectiveness. State-of-the-art results are achieved even on more detailed part-segmentation, Pascal-Animals, by only training on coarse-grained datasets. Thorough ablation studies are performed to dissect each component, both quantitatively and qualitatively.

Annotation-free Audio-Visual Segmentation

The objective of Audio-Visual Segmentation (AVS) is to locate sounding objects within visual scenes by accurately predicting pixelwise segmentation masks. In this paper, we present the following contributions: (i), we propose a scalable and annotation-free pipeline for generating artificial data for the AVS task. We leverage existing image segmentation and audio datasets to draw links between category labels, image-mask pairs, and audio samples, which allows us to easily compose (image, audio, mask) triplets for training AVS models; (ii), we introduce a novel Audio-Aware Transformer (AuTR) architecture that features an audio-aware query-based transformer decoder. This architecture enables the model to search for sounding objects with the guidance of audio signals, resulting in more accurate segmentation; (iii), we present extensive experiments conducted on both synthetic and real datasets, which demonstrate the effectiveness of training AVS models with synthetic data generated by our proposed pipeline. Additionally, our proposed AuTR architecture exhibits superior performance and strong generalization ability on public benchmarks. The project page is https://jinxiang-liu.github.io/anno-free-AVS/.

Multi-modal Prompting for Low-Shot Temporal Action Localization

In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos, even not seen at training time. We adopt a Transformer-based two-stage action localization architecture with class-agnostic action proposal, followed by open-vocabulary classification. We make the following contributions. First, to compensate image-text foundation models with temporal motions, we improve category-agnostic action proposal by explicitly aligning embeddings of optical flows, RGB and texts, which has largely been ignored in existing low-shot methods. Second, to improve open-vocabulary action classification, we construct classifiers with strong discriminative power, i.e., avoid lexical ambiguities. To be specific, we propose to prompt the pre-trained CLIP text encoder either with detailed action descriptions (acquired from large-scale language models), or visually-conditioned instance-specific prompt vectors. Third, we conduct thorough experiments and ablation studies on THUMOS14 and ActivityNet1.3, demonstrating the superior performance of our proposed model, outperforming existing state-of-the-art approaches by one significant margin.

DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we propose to exploit such knowledgeable diffusion models for mainstream discriminative tasks, i.e., unsupervised object discovery: saliency segmentation and object localization. However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use. Besides, the lack of explicitly labeled data significantly limits performance in unsupervised settings. To tackle these issues, we introduce DiffusionSeg, one novel synthesis-exploitation framework containing two-stage strategies. To alleviate data insufficiency, we synthesize abundant images, and propose a novel training-free AttentionCut to obtain masks in the first synthesis stage. In the second exploitation stage, to bridge the structural gap, we use the inversion technique, to map the given image back to diffusion features. These features can be directly used by downstream architectures. Extensive experiments and ablation studies demonstrate the superiority of adapting diffusion for unsupervised object discovery.

Constraint and Union for Partially-Supervised Temporal Sentence Grounding

Temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great performance but requires expensive annotation costs; while the weakly-supervised setting adopts cheap labels but performs poorly. To pursue high performance with less annotation cost, this paper introduces an intermediate partially-supervised setting, i.e., only short-clip or even single-frame labels are available during training. To take full advantage of partial labels, we propose a novel quadruple constraint pipeline to comprehensively shape event-query aligned representations, covering intra- and inter-samples, uni- and multi-modalities. The former raises intra-cluster compactness and inter-cluster separability; while the latter enables event-background separation and event-query gather. To achieve more powerful performance with explicit grounding optimization, we further introduce a partial-full union framework, i.e., bridging with an additional fully-supervised branch, to enjoy its impressive grounding bonus, and be robust to partial annotations. Extensive experiments and ablations on Charades-STA and ActivityNet Captions demonstrate the significance of partial supervision and our superior performance.

Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization

Weakly-supervised temporal action localization (WTAL) learns to detect and classify action instances with only category labels. Most methods widely adopt the off-the-shelf Classification-Based Pre-training (CBP) to generate video features for action localization. However, the different optimization objectives between classification and localization, make temporally localized results suffer from the serious incomplete issue. To tackle this issue without additional annotations, this paper considers to distill free action knowledge from Vision-Language Pre-training (VLP), since we surprisingly observe that the localization results of vanilla VLP have an over-complete issue, which is just complementary to the CBP results. To fuse such complementarity, we propose a novel distillation-collaboration framework with two branches acting as CBP and VLP respectively. The framework is optimized through a dual-branch alternate training strategy. Specifically, during the B step, we distill the confident background pseudo-labels from the CBP branch; while during the F step, the confident foreground pseudo-labels are distilled from the VLP branch. And as a result, the dual-branch complementarity is effectively fused to promote a strong alliance. Extensive experiments and ablation studies on THUMOS14 and ActivityNet1.2 reveal that our method significantly outperforms state-of-the-art methods.

Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation

We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the effects of data augmentations, and reveal that (1) composition of data augmentations plays a critical role, {\em i.e.}~explicitly encouraging the audio-visual representations to be invariant to various transformations~({\em transformation invariance}); (2) enforcing geometric consistency substantially improves the quality of learned representations, {\em i.e.}~the detected sound source should follow the same transformation applied on input video frames~({\em transformation equivariance}). Extensive experiments demonstrate that our model significantly outperforms previous methods on two sound localization benchmarks, namely, Flickr-SoundNet and VGG-Sound. Additionally, we also evaluate audio retrieval and cross-modal retrieval tasks. In both cases, our self-supervised models demonstrate superior retrieval performances, even competitive with the supervised approach in audio retrieval. This reveals the proposed framework learns strong multi-modal representations that are beneficial to sound localisation and generalization to further applications. \textit{All codes will be available}.

Prompting Visual-Language Models for Efficient Video Understanding

Visual-language pre-training has shown great success for learning joint visual-textual representations from large-scale web data, demonstrating remarkable ability for zero-shot generalisation. This paper presents a simple method to efficiently adapt one pre-trained visual-language model to novel tasks with minimal training, and here, we consider video understanding tasks. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert the novel tasks into the same format as the pre-training objectives. In addition, to bridge the gap between static images and videos, temporal information is encoded with lightweight Transformers stacking on top of frame-wise visual features. Experimentally, we conduct extensive ablation studies to analyse the critical components and necessities. On 9 public benchmarks of action recognition, action localisation, and text-video retrieval, across closed-set, few-shot, open-set scenarios, we achieve competitive or state-of-the-art performance to existing methods, despite training significantly fewer parameters.