Related papers: AnyMS: Bottom-up Attention Decoupling for Layout-g…
Cross-domain Few-shot Medical Image Segmentation (CD-FSMIS) is a potential solution for segmenting medical images with limited annotation using knowledge from other domains. The significant performance of current CD-FSMIS models relies on…
Subject-driven image inpainting has recently gained prominence in image editing with the rapid advancement of diffusion models. Beyond image guidance, recent studies have explored incorporating text guidance to achieve identity-preserved…
Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-driven controllability.…
Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding…
Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive…
Multi-label image recognition in the low-label regime is a task of great challenge and practical significance. Previous works have focused on learning the alignment between textual and visual spaces to compensate for limited image labels,…
In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited…
Few-shot multi-class anomaly detection is crucial in real industrial settings, where only a few normal samples are available while numerous object types must be inspected. This setting is challenging as defect patterns vary widely across…
Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challenging. We identify a key underlying cause: attention collapse…
In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Layout-Aware Multi-Image Composition framework that, for the…
Cross-subject visual decoding aims to reconstruct visual experiences from brain activity across individuals, enabling more scalable and practical brain-computer interfaces. However, existing methods often suffer from degraded performance…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encountering challenges such as compromised object integrity,…
Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm,…
Existing subject-driven text-to-image generation models suffer from tedious fine-tuning steps and struggle to maintain both text-image alignment and subject fidelity. For generating compositional subjects, it often encounters problems such…
Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…
Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for…
Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive…
Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale…
Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to textual queries. To directly adapt this for localization in a training-free manner, we cast video reasoning…