- 🌱 Currently exploring multimodal feature alignment, feature representation, open-vocab object detection, fairness, and VLM finetuning
Highlights
- Pro
Pinned Loading
-
DL_cyber_attacks
DL_cyber_attacks PublicImplementation of Backdoor Attacks and Defenses on Resnet18 and EfficientNetB0. We have implemented Bad Nets and Data Poisoning attacks,along with Neural Cleanse,Fine-Pruning and Jittering defenses…
Python 5
-
geo-image-retrieval
geo-image-retrieval PublicForked from onatakca/geo-image-retrieval
Comparing linear evaluation and pooling methods of vision encoders (DINOv3, Perception Encoder, CLIP and StreetCLIP) on MSLS London dataset for image-to-image retrieval.
Jupyter Notebook
-
melanoma-classification
melanoma-classification PublicFair and debiased skin lesion melanoma classification code. Using recall based cross-entropy loss combined with domain-discriminative training for equal perforamnce across all skin color groups.
Jupyter Notebook
-
gemma3_lora_ft_vs_icl
gemma3_lora_ft_vs_icl PublicComparing Gemma3 models performance (270m,1b and 4b) on classification, reasoning and QA suite using ICL vs LoRA finetuning. Comparing performance to BERT trained on classification and QA.
Jupyter Notebook
-
egocentric_video_graph_framework_ar
egocentric_video_graph_framework_ar PublicGraph-Based Framework for Activity Recognition in Egocentric Videos
Jupyter Notebook
-
synchain-absa-emotion
synchain-absa-emotion PublicForked from onatakca/synchain-absa-emotion
Knowledge distillation in aspect-based sentiment and emotion analysis using QWEN2.5-32B as teacher and QWEN2.5-7B and LLaMA3-8B as student models
Jupyter Notebook
If the problem persists, check the GitHub status page or contact support.


