Dipam Goswami

6 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

CVPR (2) ECCV (1) ICCV (1) NeurIPS (1) WACV (1)

Top co-authors

Joost van de Weijer (6) Yuyang Liu (3) Bartłomiej Twardowski (2) Albin Soutif-Cormerais (1) Simone Magistri (1) Xialei Liu (1) Sandesh Kamath (1) Didier Stricker (1) Yang Cong (1) Bart?omiej Twardowski (1)

Research topics

Machine Learning (5) Learning Types (5) Computer Vision (3) Analysis (2) Core Methods (2) Deep Learning (1) Applications (1) Models (1)

Keywords

catastrophic forgetting (4) continual learning (2) class-incremental learning (2) image retrieval (1) feature distribution (1) foreground detection (1) spectral analysis (1) adversarial perturbation (1) vision-language model (1) weight transfer (1) replay memory (1) exemplar-free learning (1) cosine similarity (1) prototypical network (1) intra-modal alignment (1) incremental object detection (1) contrastive learning (1) prototype drift (1) semantic segmentation (1) image segmentation (1)

Papers

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment CVPR 2026 Exemplar-free Continual Representation Learning via Learnable Drift Compensation ECCV 2024 Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning CVPR 2024 Attribution-Aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation WACV 2023 Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection ICCV 2023 FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning NeurIPS 2023