DIFFCZSL is proposed, a diffusion-augmented framework that injects generative priors from pre-trained diffusion models into CLIP-based CZSL pipelines and highlights the complementary strengths of generative diffusion representations and discriminative vision-language models for compositional generalization.
Abstract
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions. Although recent works achieve impressive performance in CZSL by leveraging large vision-language models, they primarily rely on discriminative representations that may not explicitly preserve the structured relationships between primitive concepts and their compositions. Motivated by the recent success of diffusion-based classifiers and their competitive performance relative to discriminative models, we investigate whether intermediate diffusion representations can provide complementary cues for CZSL. To this end, we propose DIFFCZSL, a diffusion-augmented framework that injects generative priors from pre-trained diffusion models into CLIP-based CZSL pipelines. We extract intermediate diffusion representations and project them into the CLIP embedding space to provide auxiliary supervision on both image and text modalities. Through contrastive alignment between CLIP embeddings and diffusion features during training, our method encourages the embedding geometry toward richer composition-aware semantics, while introducing no additional cost at inference time. Extensive experiments on three public CZSL benchmarks demonstrate consistent improvements over strong CLIP-based baselines under both closed-world and open-world settings. Our results highlight the complementary strengths of generative diffusion representations and discriminative vision-language models for compositional generalization.
Open-world entity segmentation aims to predict masks for arbitrary objects across domains and at multiple granularities, from parts to whole objects. In this setting, SAM sets a strong standard: trained on SA-1B, comprising 11M images and over 1B carefully annotated masks, it achieves remarkable zero-shot performance. Collecting such labels is expensive and time-consuming, however, which limits how far this recipe can scale. Text-to-image diffusion models offer a way around this. Their intermediate features transfer well across perception tasks, and since object structure emerges as the model denoises a noise sample into an image conditioned on a text prompt, that structure is already encoded in these representations. They can therefore be exploited for open-world entity segmentation without retraining or supervision. Building on this observation, we introduce Diffuse2Seg, which repurposes generative diffusion models for automatic mask generation by propagating a grid of point prompts through their self-attention representations in an edge-preserving manner. Diffuse2Seg produces multi-granular instance masks and outperforms prior state-of-the-art label generators by 4.3-7.1 p.p. in AR_1000 across five domains. Training an instance segmentation model on these generated masks advances detector-free open-world segmentation by 7.4 and 7.7 p.p. on"things"and"stuff+things"datasets and surpasses the detector-based UnSAM on"stuff+things"by 2.1 p.p. in AR_1000. Finally, we show that a model trained on Diffuse2Seg labels provides a strong initialization for semi-supervised learning, outperforming its fully supervised counterpart with already 5k labeled images.
Christoph Hümmer, Joachim Sicking, Fabian Hüger et al.· 0 citations
MLDA is introduced, a test-time adaptation framework for CZSL that jointly derives multi-level prototypes and performs dynamic vision–language alignment and leverages optimal transport to achieve consistent matching of semantically salient information across modalities.
Miao-Ge Li, Yu Liu, Jingcai Guo· Proceedings of the Thirty-Fi...· 0 citations
The results indicate that diffusion transformers carry more concept-level information than current attribution methods recover, and that much of it is lost on the way to the mask rather than absent from the model.
Rajatsubhra Chakraborty, Xu-Jun Che, Ritabrata Chakraborty et al.· 0 citations
Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts to be learned with only image-level supervision. We introduce DR.WILSS, an innovative approach to address catastrophic forgetting in continual learning using diffusion-based generative replay. Our framework leverages language clues to guide the diffusion process, employing self-inpainting and regularization techniques to efficiently produce replay data, aiding the learning process. By generating high-quality replay data, the information from previously learned classes can be preserved during continual updates, a critical challenge in incremental learning scenarios. To further align the statistics of replay data with those of training samples, we apply LoRAs to the generative model. Experimental results demonstrate state-of-the-art performance across multiple benchmarks and generative architectures, while avoiding storage of training data and the use of additional resource-demanding tools during training. The proposed technique enables an optimal tradeoff between training complexity and inference-time accuracy, making DR.WILSS a promising solution for real-world applications.
Leon Arthur Marx, Francesco Barbato, Matteo Caligiuri et al.· 0 citations
Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer strong regularization effects, their combined use has saturated in performance due to overlapping functionalities, and aggressive pixel-level manipulations may disrupt delicate cross-modal alignment. This saturation motivates the search for a new augmentation axis within the embedding space rather than the input space. We introduce Aether, a simple plug-in method that applies diffusion-style random perturbations in the embedding space via controlled alpha-mixing, specifically designed to provide isotropic regularization that remains semantically consistent. Inspired by feature-space perturbations in language models and image degradation in generative pretraining, Aether induces mild yet effective perturbations that smooth the representations without compromising the fine-grained structural information required for strong vision-language encoders. Across diverse architectures and across multiple recognition tasks, Aether delivers consistent gains over the advanced recipe combining CutMix, Mixup, DropPath, and RandAug---a level of improvement rarely observed with modern augmentation alternatives. Notably, Aether demonstrates superior effectiveness in multi-modal alignment, succeeding where traditional pixel-space augmentations fail by providing a stable, isotropic regularization signal that respects the integrity of the high-dimensional feature space.
Hyesong Choi, Daeun Kim, Song Park et al.· 0 citations
Self-supervised representation-guided generative dataset distillation (SRG) is proposed, a framework that translates the SSL geometry into diffusion guidance and consistently outperforms the evaluated generative baselines across multiple datasets and IPC settings.
Mingzhuo Li, Guang Li, Linfeng Ye et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
