AI NEWS.ccAI is happening. The future is updating.
♡ Saved tools 0
AI NEWS · Model intelligenceExplore capabilities. Make informed choices. ↗Profiles indexed first · Details continuously enriched
THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Popular searches
84,991 model profiles13202 providers / publishers45 capability categories465 with comparable prices · 30 benchmarked
TText generation▧Image generation▷Video generation⌘Code generation◖Speech synthesis♫Music generation⬡3D modeling▤Document analysis
DISCOVER & COMPARE

Explore AI models 251

Discover models worth your attention

Talk2DINOv3-ViTB

lorebianchi98

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation (ICCV 2025) Luca Barsellotti*   Lorenzo Bianchi*   Nicola Messina   Fabio Carrara   Marcella Cornia   Lorenzo Baraldi   Fabrizio Falchi   Rita Cucchiara Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks.

Image segmentation
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This model is a fine-tuned version of nvidia/mit-b5 on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2292 - Mean Iou: 0.6258 - Mean Accuracy: 0.7547 - Overall Accuracy: 0.8256 - Accuracy Background: nan - Accuracy Hat: 0.8561 - Accuracy Hair: 0.8974 - Accuracy Sunglasses: 0.7540 - Accuracy Upper-clothes: 0.8553 - Accuracy Skirt: 0.7026 - Accuracy Pants: 0.8913 - Accuracy Dress: 0.7525 - Accuracy Belt: 0.4251 - Accuracy Left-shoe: 0.6014 - Accuracy Right-shoe: 0.6374 - Accuracy Face: 0.9094 - Accuracy Left-leg: 0.8452 - Accuracy Right-leg: 0.8343 - Accuracy Left-arm: 0.8506 - Accuracy Right-arm: 0.8287 - Accuracy Bag: 0.8232 - Accuracy Scarf: 0.3662 - Iou Background: 0.0 - Iou Hat: 0.7625 - Iou Hair: 0.8171 - Iou Sunglasses: 0.6400 - Iou Upper-clothes: 0.7700 - Iou Skirt: 0.6211 - Iou Pants: 0.7788 - Iou Dress: 0.5512 - Iou Belt: 0.3564 - Iou Left-shoe: 0.5032 - Iou Right-shoe: 0.5381 - Iou Face: 0.8294 - Iou Left-leg: 0.7412 - Iou Right-leg: 0.7591 - Iou Left-arm: 0.7579 - Iou Right-arm: 0.7705 - Iou Bag: 0.7729 - Iou Scarf: 0.2956 The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15

Image segmentation
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation. The dataset on hugging face is called "mattmdjaga/human_parsing_dataset". Labels: 0: "Background", 1: "Hat", 2: "Hair", 3: "Sunglasses", 4: "Upper-clothes", 5: "Skirt", 6: "Pants", 7: "Dress", 8: "Belt", 9: "Left-shoe", 10: "Right-shoe", 11: "Face", 12: "Left-leg", 13: "Right-leg", 14: "Left-arm", 15: "Right-arm", 16: "Bag", 17: "Scarf" Overall Evaluation Metrics: - Evaluation Loss: 0.15 - Mean Accuracy: 0.80 - Mean IoU: 0.69

Image segmentation
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on ADE20k (an important benchmark for semantic segmentation of images) at resolution 640x640. It was introduced in the paper BEIT: BERT Pre-Training of Image Transformers by Hangbo Bao, Li Dong and Furu Wei and first released in this repository. Disclaimer: The team releasing BEiT did not write a model card for this model so this model card has been written by the Hugging Face team. The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT is pretrained on a large collection of images in a self-supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. The pre-training objective for the model is to predict visual tokens from the encoder of OpenAI's DALL-E's VQ-VAE, based on masked patches. Next, the model was fine-tuned in a supervised fashion on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.

Image segmentation
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗
COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ
How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

AI NEWS · From information to decisions

Follow trends. Find tools. Explore models.

Explore AI news ↗Discover AI tools ↗