tezvyn:

🤖AI & ML

Artificial intelligence, machine learning, and data science

1166 bites

More in AI & ML — page 13

Computer Vision2 min read

Core principles of a Neural Radiance Field

WHAT IT TESTS: implicit 3D representation and differentiable rendering. OUTLINE: an MLP maps a 3D point plus view direction to color and density; novel views render by casting rays, sampling points, querying the MLP, and volume-integrating along each ray.

Computer Vision2 min read

Why ViTs need positional embeddings

WHAT IT TESTS: why order matters for attention but not convolution. OUTLINE: self-attention is permutation invariant so patch order is lost; positional embeddings restore spatial location. CNNs encode position implicitly via the fixed convolution grid.

Computer Vision89 sec read

Cross-attention for visual question answering

WHAT IT TESTS: fusing two modalities with attention. OUTLINE: in cross-attention queries come from one modality and keys/values from the other, e.g. text queries attend over image features so the question selects relevant regions.

Computer Vision2 min read

How Swin Transformer achieves linear attention

WHAT IT TESTS: making attention scale to high resolution. OUTLINE: Swin computes attention within local non-overlapping windows of fixed size, making cost linear in patches, then shifts windows between layers so information crosses boundaries.

Computer Vision2 min read

Inductive biases of ViT versus CNN

WHAT IT TESTS: how built-in priors affect data needs. OUTLINE: CNNs bake in locality and translation equivariance; a plain ViT has almost none beyond patch structure, so it must learn spatial relations from data, needing large datasets or strong pretraining.

Computer Vision88 sec read

Self-attention over image patches explained

WHAT IT TESTS: the QKV mechanism on patch tokens. OUTLINE: each patch projects to query, key, value; a patch's query is scored against all keys, softmax-normalized into weights, used to combine all values.

Computer Vision2 min read

How ViT and CNN process an image differently

WHAT IT TESTS: the input pipelines of two paradigms. OUTLINE: a CNN slides local filters over the raw pixel grid; a ViT splits the image into patches, flattens and linearly embeds each into a token, adds positional embeddings, and feeds the sequence to…

Computer Vision2 min read

Scene flow versus optical flow

WHAT IT TESTS: 2D versus 3D motion estimation. OUTLINE: optical flow is 2D pixel motion in the image plane; scene flow is the 3D motion field of points in space, needing depth via stereo, RGB-D, or LiDAR.

Computer Vision2 min read

Self-supervised pretraining for video understanding

WHAT IT TESTS: learning from unlabeled video via pretext tasks. OUTLINE: define a label-free task like temporal order prediction or contrastive clip matching that forces temporal reasoning, then fine-tune on labeled action data.

Computer Vision85 sec read

Re-identification in multi-object tracking

WHAT IT TESTS: maintaining identity across gaps and occlusions. OUTLINE: Re-ID matches an object to its prior id using appearance embeddings, not just position; store track features and match re-entering detections by embedding similarity.

Computer Vision82 sec read

3D CNNs vs two-stream action recognition

WHAT IT TESTS: how architectures capture temporal motion. OUTLINE: 3D CNNs learn spatiotemporal filters end to end but are heavy; two-stream splits RGB appearance and precomputed optical flow, strong but costly to compute flow.

Computer Vision88 sec read

Kalman filter for bounding-box tracking

WHAT IT TESTS: predict-update recursion applied to tracking. OUTLINE: state, transition, measurement models, and process plus measurement noise; predict then correct each frame. State holds box position and velocity; measurement is the detected box.

Computer Vision81 sec read

Brightness constancy and small-motion assumptions

WHAT IT TESTS: foundations and limits of optical flow. OUTLINE: brightness constancy says a point's intensity is invariant under motion; small motion lets you linearize via Taylor expansion.

Computer Vision79 sec read

Design a tracking-by-detection tracker

WHAT IT TESTS: building tracking from detection plus data association. OUTLINE: detect per frame, then associate boxes across frames by IoU or appearance using Hungarian matching, maintaining track ids.

Computer Vision78 sec read

Sparse vs dense optical flow and Lucas-Kanade

WHAT IT TESTS: understanding motion estimation granularity. OUTLINE: sparse flow tracks selected feature points, dense flow computes a vector per pixel; Lucas-Kanade solves brightness constancy in a local window assuming constant motion.

Computer Vision79 sec read

Adapting ViT for dense semantic segmentation

WHAT IT TESTS: turning a classification ViT into a dense predictor. OUTLINE: reassemble patch tokens into a 2D feature map, add a decoder, and handle low resolution plus quadratic attention cost.

Computer Vision81 sec read

Explain panoptic segmentation and Panoptic Quality

WHAT IT TESTS: unifying semantic and instance segmentation plus its metric. OUTLINE: panoptic assigns every pixel a class and instance id over things and stuff; PQ factors into SQ, average IoU of matches, times RQ, an F1 over matched segments.

Computer Vision69 sec read

How to improve coarse segmentation boundaries?

WHAT IT TESTS: practical debugging of low-resolution mask edges. OUTLINE: skip connections and higher-resolution features, boundary-aware losses, and point-based or CRF refinement.

Computer Vision80 sec read

How does Mask R-CNN do instance segmentation?

WHAT IT TESTS: understanding of two-stage detectors and per-instance masks. OUTLINE: Faster R-CNN backbone plus RPN, then RoIAlign and a parallel mask head predicting per-class binary masks. RED FLAG: claiming masks are shared or that RoIPool is used.

Computer Vision86 sec read

U-Net architecture and its skip connections

WHAT IT TESTS: encoder-decoder design for segmentation. OUTLINE: U-Net has a contracting encoder, an expanding decoder, and skip connections that concatenate matching-resolution encoder features into the decoder to recover spatial detail lost in downsampling.